Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/punt-labs/postern/agents-mdgit clone --depth 1 https://github.com/punt-labs/posternWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/punt-labs/postern/agents-md)<a href="https://agentmods.dev/instructions/punt-labs/postern/agents-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/postern/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01391 | $0.01391 |
| Opus 5 | $0.00696 | $0.00696 |
| Sonnet 5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade B, and why
postern AGENTS.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
settings (for example `~/.claude/settings.json` or Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8422/help How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postern — Agent Bootstrap
Scope of this file. AGENTS.md is the runtime bootstrap for agents using Postern — the HTTP server, the
/helpendpoints, the/replevaluation flow. If you are an agent developing Postern itself (writing Smalltalk classes, refactoring, shipping releases), read CLAUDE.md instead — it covers architecture, conventions, and the contributor delegation model.
A live Smalltalk runtime is available at http://localhost:8422. You can compile
code, run tests, inspect objects, and commit — all over HTTP, without touching the IDE.
Read the server's documentation before writing any Smalltalk:
curl http://localhost:8422/help
This returns a table of contents for ten sections. Read the sections relevant to your task before starting. The content is served from the live image and reflects the actual loaded packages — not static docs.
| Section | When to read it |
|---|---|
/help/api |
First time connecting — covers endpoints, auth, request format |
/help/browse |
Read-only introspection — classes, selectors, senders, source lookup |
/help/pharo |
Before writing any Smalltalk — covers class syntax, protocols, JSON |
/help/dispatch |
Before delegating sub-tasks — TDD cycle, required elements |
/help/lint |
Before committing — lint discipline and gate |
/help/git |
Before committing — Iceberg workflow, CLI merge |
/help/testing |
Before running tests — scoped runs only |
/help/safety |
If anything behaves unexpectedly — deadlock prevention, recovery |
/help/makefile |
To restart or rebuild the image |
/help/lessons |
When something goes wrong — incident record |
To evaluate Smalltalk:
curl -s -X POST http://localhost:8422/repl \
-H "Content-Type: text/plain" \
-d "3 + 4"
# → 7
If auth is enabled, add -H "X-Eval-Token: $(cat .tmp/eval-token)".
Agent Permissions / Config
Local curl access to http://localhost:8422 may be blocked by your agent
tool sandbox unless allowlisted.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 111 lines · 1,391 tokens per session scan B db689a212704
postern AGENTS.md is an instructions file published in the GitHub repository punt-labs/postern (1 stars, last pushed 11d ago), licensed MIT. It adds 1,391 tokens to every session, about $0.0070 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
pharo-agentic-browser AGENTS.md
AGENTS.md instructions for mumez/pharo-agentic-browser, covering agents.md, general rules, implementation rules, project overview and package structure.
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
copilot-proxy-api CLAUDE.md
Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.